Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20200914195634.12881-1-sean.j.christopherson@intel.com> <20200914195634.12881-2-sean.j.christopherson@intel.com>
In-Reply-To: <20200914195634.12881-2-sean.j.christopherson@intel.com>
From:   Uros Bizjak <ubizjak@gmail.com>
Date:   Mon, 14 Sep 2020 22:37:25 +0200
Message-ID: <CAFULd4aNVW1Wzs=Y9+-wwFw2FyjHZRKe=SPkJ7uBdGmbN6i47A@mail.gmail.com>
Subject: Re: [PATCH 1/2] KVM: VMX: Move IRQ invocation to assembly subroutine
To:     Sean Christopherson <sean.j.christopherson@intel.com>
Cc:     Paolo Bonzini <pbonzini@redhat.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>, kvm@vger.kernel.org,
        LKML <linux-kernel@vger.kernel.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Andi Kleen <ak@linux.intel.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Sep 14, 2020 at 9:56 PM Sean Christopherson
<sean.j.christopherson@intel.com> wrote:
>
> Move the asm blob that invokes the appropriate IRQ handler after VM-Exit
> into a proper subroutine.  Slightly rework the blob so that it plays
> nice with objtool without any additional hints (existing hints aren't
> able to handle returning with a seemingly modified stack size).
>
> Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Cc: Uros Bizjak <ubizjak@gmail.com>
> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
> ---
>  arch/x86/kvm/vmx/vmenter.S | 28 ++++++++++++++++++++++++++++
>  arch/x86/kvm/vmx/vmx.c     | 33 +++------------------------------
>  2 files changed, 31 insertions(+), 30 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
> index 799db084a336..baec1e0fefc5 100644
> --- a/arch/x86/kvm/vmx/vmenter.S
> +++ b/arch/x86/kvm/vmx/vmenter.S
> @@ -4,6 +4,7 @@
>  #include <asm/bitsperlong.h>
>  #include <asm/kvm_vcpu_regs.h>
>  #include <asm/nospec-branch.h>
> +#include <asm/segment.h>
>
>  #define WORD_SIZE (BITS_PER_LONG / 8)
>
> @@ -294,3 +295,30 @@ SYM_FUNC_START(vmread_error_trampoline)
>
>         ret
>  SYM_FUNC_END(vmread_error_trampoline)
> +
> +SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff)
> +       /*
> +        * Unconditionally create a stack frame.  RSP needs to be aligned for
> +        * x86-64, getting the correct RSP on the stack (for x86-64) would take
> +        * two instructions anyways, and it helps make objtool happy (see below).
> +        */
> +       push %_ASM_BP
> +       mov %rsp, %_ASM_BP

_ASM_SP instead of %rsp to avoid assembly failure for 32bit targets.

> +
> +#ifdef CONFIG_X86_64
> +       push $__KERNEL_DS
> +       push %_ASM_BP
> +#endif
> +       pushf
> +       push $__KERNEL_CS
> +       CALL_NOSPEC _ASM_ARG1
> +
> +       /*
> +        * "Restore" RSP from RBP, even though IRET has already unwound RSP to
> +        * the correct value.  objtool doesn't know the target will IRET and so
> +        * thinks the stack is getting walloped (without the explicit restore).
> +        */
> +       mov %_ASM_BP, %rsp
> +       pop %_ASM_BP
> +       ret
> +SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff)
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 46ba2e03a892..391f079d9136 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -6409,6 +6409,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
>         memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
>  }
>
> +void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
> +
>  static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
>  {
>         u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
> @@ -6430,10 +6432,6 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
>  static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
>  {
>         unsigned int vector;
> -       unsigned long entry;
> -#ifdef CONFIG_X86_64
> -       unsigned long tmp;
> -#endif
>         gate_desc *desc;
>         u32 intr_info = vmx_get_intr_info(vcpu);
>
> @@ -6443,36 +6441,11 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
>
>         vector = intr_info & INTR_INFO_VECTOR_MASK;
>         desc = (gate_desc *)host_idt_base + vector;
> -       entry = gate_offset(desc);

I'd leave the above line...

>
>         kvm_before_interrupt(vcpu);
> -
> -       asm volatile(
> -#ifdef CONFIG_X86_64
> -               "mov %%rsp, %[sp]\n\t"
> -               "and $-16, %%rsp\n\t"
> -               "push %[ss]\n\t"
> -               "push %[sp]\n\t"
> -#endif
> -               "pushf\n\t"
> -               "push %[cs]\n\t"
> -               CALL_NOSPEC
> -               :
> -#ifdef CONFIG_X86_64
> -               [sp]"=&r"(tmp),
> -#endif
> -               ASM_CALL_CONSTRAINT
> -               :
> -               [thunk_target]"r"(entry),
> -#ifdef CONFIG_X86_64
> -               [ss]"i"(__KERNEL_DS),
> -#endif
> -               [cs]"i"(__KERNEL_CS)
> -       );
> -
> +       vmx_do_interrupt_nmi_irqoff(gate_offset(desc));

... to make the above line read as:

vmx_do_interrupt_nmi_irqoff(entry);

This way, it looks more descriptive to me.

Uros.

>         kvm_after_interrupt(vcpu);
>  }
> -STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff);
>
>  static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
>  {
> --
> 2.28.0
>